JAL-3076 refactor for more efficient scan of 'gene' features

[jalview.git] / src / jalview / ext / ensembl / EnsemblProtein.java

diff --git a/src/jalview/ext/ensembl/EnsemblProtein.java b/src/jalview/ext/ensembl/EnsemblProtein.java
index 29c7eda..0280f16 100644 (file)
--- a/src/jalview/ext/ensembl/EnsemblProtein.java
+++ b/src/jalview/ext/ensembl/EnsemblProtein.java
@@ -1,27 +1,68 @@
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ * 
+ * This file is part of Jalview.
+ * 
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License 
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *  
+ * Jalview is distributed in the hope that it will be useful, but 
+ * WITHOUT ANY WARRANTY; without even the implied warranty 
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR 
+ * PURPOSE.  See the GNU General Public License for more details.
+ * 
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview.  If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
 package jalview.ext.ensembl;
 
 import jalview.datamodel.AlignmentI;
 import jalview.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
 
-import java.util.Arrays;
+import java.util.ArrayList;
 import java.util.List;
 
 import com.stevesoft.pat.Regex;
 
+/**
+ * A client to fetch protein translated sequence for an Ensembl identifier
+ * 
+ * @author gmcarstairs
+ *
+ */
 public class EnsemblProtein extends EnsemblSeqProxy
 {
-  // TODO modify to accept other species e.g. ENSMUSPnnn
+  /*
+   * accepts ENSP with 11 digits
+   * or ENSMUSP or similar for other species
+   * or CCDSnnnnn.nn with at least 3 digits
+   */
   private static final Regex ACCESSION_REGEX = new Regex(
-          "(ENSP|CCDS)[0-9.]{3,}$");
-
-  private static final List<String> CROSSREFS = Arrays.asList(new String[] {
-      "PDB", "Uniprot/SPTREMBL", "Uniprot/SWISSPROT" });
+          "(ENS([A-Z]{3}|)P[0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
 
+  /**
+   * Default constructor (to use rest.ensembl.org)
+   */
   public EnsemblProtein()
   {
     super();
   }
 
+  /**
+   * Constructor given the target domain to fetch data from
+   * 
+   * @param d
+   */
+  public EnsemblProtein(String d)
+  {
+    super(d);
+  }
+
   @Override
   public String getDbName()
   {
@@ -69,16 +110,10 @@ public class EnsemblProtein extends EnsemblSeqProxy
   }
 
   @Override
-  protected boolean identifiesSequence(SequenceFeature sf, String accId)
-  {
-    // not applicable - protein sequence is not a 'subset' of genomic sequence
-    return false;
-  }
-
-  @Override
-  protected List<String> getCrossReferenceDatabases()
+  protected List<SequenceFeature> getIdentifyingFeatures(SequenceI seq,
+          String accId)
   {
-    return CROSSREFS;
+    return new ArrayList<>();
   }
 
   @Override